English
Related papers

Related papers: Data-Efficient Double-Win Lottery Tickets from Rob…

200 papers

Transfer learning aims to leverage knowledge from pre-trained models to benefit the target task. Prior transfer learning work mainly transfers from a single model. However, with the emergence of deep models pre-trained from different…

Machine Learning · Computer Science 2022-11-07 Yang Shu , Zhangjie Cao , Ziyang Zhang , Jianmin Wang , Mingsheng Long

Large-scale pre-training followed by downstream fine-tuning is an effective solution for transferring deep-learning-based models. Since finetuning all possible pre-trained models is computational costly, we aim to predict the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Zhao Wang , Aoxue Li , Zhenguo Li , Qi Dou

Spiking Neural Networks (SNNs) have recently emerged as a new generation of low-power deep neural networks, which is suitable to be implemented on low-power mobile/edge devices. As such devices have limited memory storage, neural pruning on…

Artificial Intelligence · Computer Science 2022-07-22 Youngeun Kim , Yuhang Li , Hyoungseob Park , Yeshwanth Venkatesha , Ruokai Yin , Priyadarshini Panda

With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, preference optimization, and transfer learning have all been…

Machine Learning · Statistics 2025-07-09 Javan Tahir , Surya Ganguli , Grant M. Rotskoff

Deep learning models have provided extremely successful solutions in most audio application fields. However, the high accuracy of these models comes at the expense of a tremendous computation cost. This aspect is almost always overlooked in…

Machine Learning · Computer Science 2020-08-03 Philippe Esling , Ninon Devis , Adrien Bitton , Antoine Caillon , Axel Chemla--Romeu-Santos , Constance Douwes

Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training is to learn text representations that are useful for…

Computation and Language · Computer Science 2020-04-14 Shangwen Lv , Yuechen Wang , Daya Guo , Duyu Tang , Nan Duan , Fuqing Zhu , Ming Gong , Linjun Shou , Ryan Ma , Daxin Jiang , Guihong Cao , Ming Zhou , Songlin Hu

Supervised learning systems are trained using historical data and, if the data was tainted by discrimination, they may unintentionally learn to discriminate against protected groups. We propose that fair learning methods, despite training…

Machine Learning · Computer Science 2026-01-22 Przemyslaw A. Grabowicz , Nicholas Perello , Kenta Takatsu

In Federated Learning, model training is performed across multiple computing devices, where only parameters are shared with a common central server without exchanging their data instances. This strategy assumes abundance of resources on…

Machine Learning · Computer Science 2023-09-06 Indrajeet Kumar Sinha , Shekhar Verma , Krishna Pratap Singh

Transfer learning is a widely used method to build high performing computer vision models. In this paper, we study the efficacy of transfer learning by examining how the choice of data impacts performance. We find that more pre-training…

Computer Vision and Pattern Recognition · Computer Science 2018-12-13 Jiquan Ngiam , Daiyi Peng , Vijay Vasudevan , Simon Kornblith , Quoc V. Le , Ruoming Pang

In this work, we develop a method named Twinning, for partitioning a dataset into statistically similar twin sets. Twinning is based on SPlit, a recently proposed model-independent method for optimally splitting a dataset into training and…

Machine Learning · Statistics 2022-02-17 Akhil Vakayil , V. Roshan Joseph

The underlying loss landscapes of deep neural networks have a great impact on their training, but they have mainly been studied theoretically due to computational constraints. This work vastly reduces the time required to compute such loss…

Machine Learning · Computer Science 2021-12-17 Robert Bain

Despite the great success of deep learning, recent works show that large deep neural networks are often highly redundant and can be significantly reduced in size. However, the theoretical question of how much we can prune a neural network…

Machine Learning · Computer Science 2020-11-02 Mao Ye , Lemeng Wu , Qiang Liu

Existing subset selection methods for efficient learning predominantly employ discrete combinatorial and model-specific approaches which lack generalizability. For an unseen architecture, one cannot use the subset chosen for a different…

Machine Learning · Computer Science 2024-09-20 Eeshaan Jain , Tushar Nandy , Gaurav Aggarwal , Ashish Tendulkar , Rishabh Iyer , Abir De

Deep learning techniques have revolutionised medical imaging, improving diagnostic accuracy and enabling both more accurate and earlier disease detection. However, the relationship between pre-training strategies and downstream performance…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Felix Krones

Pretraining has become a standard technique in computer vision and natural language processing, which usually helps to improve performance substantially. Previously, the most dominant pretraining method is transfer learning (TL), which uses…

Computer Vision and Pattern Recognition · Computer Science 2020-07-09 Xingyi Yang , Xuehai He , Yuxiao Liang , Yue Yang , Shanghang Zhang , Pengtao Xie

Over-parameterization of deep neural networks (DNNs) has shown high prediction accuracy for many applications. Although effective, the large number of parameters hinders its popularity on resource-limited devices and has an outsize…

Machine Learning · Computer Science 2023-04-25 Shaoyi Huang , Bowen Lei , Dongkuan Xu , Hongwu Peng , Yue Sun , Mimi Xie , Caiwen Ding

Adversarial attacks are considered the intrinsic vulnerability of CNNs. Defense strategies designed for attacks have been stuck in the adversarial attack-defense arms race, reflecting the imbalance between attack and defense. Dynamic…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Qi Peng , Wenlin Liu , Ruoxi Qin , Libin Hou , Bin Yan , Linyuan Wang

Lottery ticket hypothesis for deep neural networks emphasizes the importance of initialization used to re-train the sparser networks obtained using the iterative magnitude pruning process. An explanation for why the specific initialization…

Machine Learning · Computer Science 2024-06-26 Tausifa Jan Saleem , Ramanjit Ahuja , Surendra Prasad , Brejesh Lall

Pretrained transformer models have achieved state-of-the-art results in many tasks and benchmarks recently. Many state-of-the-art Language Models (LMs), however, do not scale well above the threshold of 512 input tokens. In specialized…

Computation and Language · Computer Science 2022-12-01 Joel Niklaus , Daniele Giofré

This thesis delves into the intricate world of Deep Neural Networks (DNNs), focusing on the exciting concept of the Lottery Ticket Hypothesis (LTH). The LTH posits that within extensive DNNs, smaller, trainable subnetworks termed "winning…

Machine Learning · Computer Science 2023-08-08 Abu-Al Hassan